Detection of the Anaerobic Threshold from Cardiopulmonary Exercise Test Data with EO-Attention-LSTM

The physiological indicators at the anaerobic threshold play an essential role in guiding scientific exercise. The gold standard methodology for detecting the anaerobic threshold is expert visual inspection, but its efficiency is low. Given the above problems, we propose an anaerobic threshold detection method combining the equilibrium optimizer (EO) algorithm and Attention-LSTM, which was verified on the data of 334 cardiopulmonary exercise tests. Through comparative experiments, the coefficient of determination (R2) of the Attention-LSTM anaerobic threshold detection model is 0.797, the R2 of the Attention-LSTM model after hyperparameter optimization by EO is 0.834. The results show that the detection error of the anaerobic threshold detection model proposed in this paper is consistent with that of experts, which can provide a certain reference value.